Merge branch 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6

* 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6: (225 commits)
  [PATCH] Don't set calgary iommu as default y
  [PATCH] i386/x86-64: New Intel feature flags
  [PATCH] x86: Add a cumulative thermal throttle event counter.
  [PATCH] i386: Make the jiffies compares use the 64bit safe macros.
  [PATCH] x86: Refactor thermal throttle processing
  [PATCH] Add 64bit jiffies compares (for use with get_jiffies_64)
  [PATCH] Fix unwinder warning in traps.c
  [PATCH] x86: Allow disabling early pci scans with pci=noearly or disallowing conf1
  [PATCH] x86: Move direct PCI scanning functions out of line
  [PATCH] i386/x86-64: Make all early PCI scans dependent on CONFIG_PCI
  [PATCH] Don't leak NT bit into next task
  [PATCH] i386/x86-64: Work around gcc bug with noreturn functions in unwinder
  [PATCH] Fix some broken white space in ia32_signal.c
  [PATCH] Initialize argument registers for 32bit signal handlers.
  [PATCH] Remove all traces of signal number conversion
  [PATCH] Don't synchronize time reading on single core AMD systems
  [PATCH] Remove outdated comment in x86-64 mmconfig code
  [PATCH] Use string instructions for Core2 copy/clear
  [PATCH] x86: - restore i8259A eoi status on resume
  [PATCH] i386: Split multi-line printk in oops output.
  ...

1 files changed, 55 insertions, 39 deletions

diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 7700e6cd2bd9..1c255ee76e7c 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -24,6 +24,8 @@
 #include <linux/device.h>
 #include <linux/sysdev.h>
 #include <linux/bcd.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
 #include <linux/kallsyms.h>
 #include <linux/acpi.h>
 #ifdef CONFIG_ACPI
@@ -39,9 +41,7 @@
 #include <asm/sections.h>
 #include <linux/cpufreq.h>
 #include <linux/hpet.h>
-#ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/apic.h>
-#endif
 
 #ifdef CONFIG_CPU_FREQ
 static void cpufreq_delayed_get(void);
@@ -49,7 +49,7 @@ static void cpufreq_delayed_get(void);
 extern void i8254_timer_resume(void);
 extern int using_apic_timer;
 
-static char *time_init_gtod(void);
+static char *timename = NULL;
 
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL(rtc_lock);
@@ -187,20 +187,15 @@ unsigned long profile_pc(struct pt_regs *regs)
 {
         unsigned long pc = instruction_pointer(regs);
 
-        /* Assume the lock function has either no stack frame or only a single 
-           word.  This checks if the address on the stack looks like a kernel 
-           text address.
-           There is a small window for false hits, but in that case the tick
-           is just accounted to the spinlock function.
-           Better would be to write these functions in assembler again
-           and check exactly. */
+        /* Assume the lock function has either no stack frame or a copy
+           of eflags from PUSHF
+           Eflags always has bits 22 and up cleared unlike kernel addresses. */
         if (!user_mode(regs) && in_lock_functions(pc)) {
-                char *v = *(char **)regs->rsp;
-                if ((v >= _stext && v <= _etext) ||
-                        (v >= _sinittext && v <= _einittext) ||
-                        (v >= (char *)MODULES_VADDR  && v <= (char *)MODULES_END))
-                        return (unsigned long)v;
-                return ((unsigned long *)regs->rsp)[1];
+                unsigned long *sp = (unsigned long *)regs->rsp;
+                if (sp[0] >> 22)
+                        return sp[0];
+                if (sp[1] >> 22)
+                        return sp[1];
         }
         return pc;
 }
@@ -281,6 +276,7 @@ static void set_rtc_mmss(unsigned long nowtime)
  *              Note: This function is required to return accurate
  *              time even in the absence of multiple timer ticks.
  */
+static inline unsigned long long cycles_2_ns(unsigned long long cyc);
 unsigned long long monotonic_clock(void)
 {
         unsigned long seq;
@@ -305,8 +301,7 @@ unsigned long long monotonic_clock(void)
                         base = monotonic_base;
                 } while (read_seqretry(&xtime_lock, seq));
                 this_offset = get_cycles_sync();
-                /* FIXME: 1000 or 1000000? */
-                offset = (this_offset - last_offset)*1000 / cpu_khz;
+                offset = cycles_2_ns(this_offset - last_offset);
         }
         return base + offset;
 }
@@ -410,8 +405,7 @@ void main_timer_handler(struct pt_regs *regs)
                         offset %= USEC_PER_TICK;
                 }
 
-                /* FIXME: 1000 or 1000000? */
-                monotonic_base += (tsc - vxtime.last_tsc) * 1000000 / cpu_khz;
+                monotonic_base += cycles_2_ns(tsc - vxtime.last_tsc);
 
                 vxtime.last_tsc = tsc - vxtime.quot * delay / vxtime.tsc_quot;
 
@@ -441,12 +435,8 @@ void main_timer_handler(struct pt_regs *regs)
  * have to call the local interrupt handler.
  */
 
-#ifndef CONFIG_X86_LOCAL_APIC
-        profile_tick(CPU_PROFILING, regs);
-#else
         if (!using_apic_timer)
                 smp_local_timer_interrupt(regs);
-#endif
 
 /*
  * If we have an externally synchronized Linux clock, then update CMOS clock
@@ -470,10 +460,8 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
         if (apic_runs_main_timer > 1)
                 return IRQ_HANDLED;
         main_timer_handler(regs);
-#ifdef CONFIG_X86_LOCAL_APIC
         if (using_apic_timer)
                 smp_send_timer_broadcast_ipi();
-#endif
         return IRQ_HANDLED;
 }
 
@@ -893,11 +881,17 @@ static struct irqaction irq0 = {
         timer_interrupt, IRQF_DISABLED, CPU_MASK_NONE, "timer", NULL, NULL
 };
 
-void __init time_init(void)
+static int __cpuinit
+time_cpu_notifier(struct notifier_block *nb, unsigned long action, void *hcpu)
 {
-        char *timename;
-        char *gtod;
+        unsigned cpu = (unsigned long) hcpu;
+        if (action == CPU_ONLINE)
+                vsyscall_set_cpu(cpu);
+        return NOTIFY_DONE;
+}
 
+void __init time_init(void)
+{
         if (nohpet)
                 vxtime.hpet_address = 0;
 
@@ -931,18 +925,17 @@ void __init time_init(void)
         }
 
         vxtime.mode = VXTIME_TSC;
-        gtod = time_init_gtod();
-
-        printk(KERN_INFO "time.c: Using %ld.%06ld MHz WALL %s GTOD %s timer.\n",
-               vxtime_hz / 1000000, vxtime_hz % 1000000, timename, gtod);
-        printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
-                cpu_khz / 1000, cpu_khz % 1000);
         vxtime.quot = (USEC_PER_SEC << US_SCALE) / vxtime_hz;
         vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz;
         vxtime.last_tsc = get_cycles_sync();
+        set_cyc2ns_scale(cpu_khz);
         setup_irq(0, &irq0);
+        hotcpu_notifier(time_cpu_notifier, 0);
+        time_cpu_notifier(NULL, CPU_ONLINE, (void *)(long)smp_processor_id());
 
-        set_cyc2ns_scale(cpu_khz);
+#ifndef CONFIG_SMP
+        time_init_gtod();
+#endif
 }
 
 /*
@@ -973,12 +966,18 @@ __cpuinit int unsynchronized_tsc(void)
 /*
  * Decide what mode gettimeofday should use.
  */
-__init static char *time_init_gtod(void)
+void time_init_gtod(void)
 {
         char *timetype;
 
         if (unsynchronized_tsc())
                 notsc = 1;
+
+        if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP))
+                vgetcpu_mode = VGETCPU_RDTSCP;
+        else
+                vgetcpu_mode = VGETCPU_LSL;
+
         if (vxtime.hpet_address && notsc) {
                 timetype = hpet_use_timer ? "HPET" : "PIT/HPET";
                 if (hpet_use_timer)
@@ -1001,7 +1000,16 @@ __init static char *time_init_gtod(void)
                 timetype = hpet_use_timer ? "HPET/TSC" : "PIT/TSC";
                 vxtime.mode = VXTIME_TSC;
         }
-        return timetype;
+
+        printk(KERN_INFO "time.c: Using %ld.%06ld MHz WALL %s GTOD %s timer.\n",
+               vxtime_hz / 1000000, vxtime_hz % 1000000, timename, timetype);
+        printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
+                cpu_khz / 1000, cpu_khz % 1000);
+        vxtime.quot = (USEC_PER_SEC << US_SCALE) / vxtime_hz;
+        vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz;
+        vxtime.last_tsc = get_cycles_sync();
+
+        set_cyc2ns_scale(cpu_khz);
 }
 
 __setup("report_lost_ticks", time_setup);
@@ -1031,8 +1039,16 @@ static int timer_resume(struct sys_device *dev)
         unsigned long flags;
         unsigned long sec;
         unsigned long ctime = get_cmos_time();
-        unsigned long sleep_length = (ctime - sleep_start) * HZ;
+        long sleep_length = (ctime - sleep_start) * HZ;
 
+        if (sleep_length < 0) {
+                printk(KERN_WARNING "Time skew detected in timer resume!\n");
+                /* The time after the resume must not be earlier than the time
+                 * before the suspend or some nasty things will happen
+                 */
+                sleep_length = 0;
+                ctime = sleep_start;
+        }
         if (vxtime.hpet_address)
                 hpet_reenable();
         else